SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 27512760 of 10420 papers

TitleStatusHype
Channel Pruning via Multi-Criteria based on Weight Dependency0
A Novel BGCapsule Network for Text Classification0
Efficient Maximal Coding Rate Reduction by Variational Forms0
Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture0
A Novel Automated Classification and Segmentation for COVID-19 using 3D CT Scans0
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks0
Chain of Thought Prompt Tuning in Vision Language Models0
A Novel Approach using CapsNet and Deep Belief Network for Detection and Identification of Oral Leukopenia0
Efficient Masked Autoencoders with Self-Consistency0
Efficient Model-Agnostic Multi-Group Equivariant Networks0
Show:102550
← PrevPage 276 of 1042Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified